RuntimeError: Error(s) in loading state_dict for DeepGCN: size mismatch for pos_embed: copying a param with shape torch.Size([1, 192, 14, 14]) from checkpoint, the shape in current model is torch.Size([1, 80, 56, 56]).

huawei-noah / Efficient-AI-Backbones

Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.

4.07k stars 708 forks source link

RuntimeError: Error(s) in loading state_dict for DeepGCN: size mismatch for pos_embed: copying a param with shape torch.Size([1, 192, 14, 14]) from checkpoint, the shape in current model is torch.Size([1, 80, 56, 56]). #226

Closed Mrx-yang closed 1 year ago

Mrx-yang commented 1 year ago

After downloading the ImageNet dataset and the pretrained model online，I run the command “python train.py imagenet/train/ --model pvig_s_224_gelu -b 32 --pretrain_path pretrained/vig_ti_74.5.pth --evaluate” ，but occur this mistake above， how do i solve it？

iamhankai commented 1 year ago

please refer to https://github.com/huawei-noah/Efficient-AI-Backbones/issues/219